Multipose Face Recognition-Based Combined Adaptive Deep Learning Vector Quantization

Table 6

Recognition accuracy of the 40 occluded facial images with different block sizes.

Image size format	SDUMLA-HMT	CASIA-V5
5 × 5	93.25	92.65
6 × 6	90.36	90.05
8 × 8	90.01	89.25
10 × 40	85.54	85.08